Versioned name: Mish-4

Category: Activation function

Short description: Mish is a Self Regularized Non-Monotonic Neural Activation Function.

Detailed description

Mish is a self regularized non-monotonic neural activation function proposed in this article.

Mish performs element-wise activation function on a given input tensor, based on the following mathematical formula:

\[Mish(x) = x\cdot\tanh\big(SoftPlus(x)\big) = x\cdot\tanh\big(\ln(1+e^{x})\big)\]

Attributes: Mish operation has no attributes.


  • 1: A tensor of type T and arbitrary shape. Required.


  • 1: The result of element-wise Mish function applied to the input tensor. A tensor of type T and the same shape as input tensor.


  • T: arbitrary supported floating-point type.


<layer ... type="Mish">
        <port id="0">
        <port id="3">